Internet-of-things system and method for optimizing production scheduling of garment factory cutting bed and cloth paving machine

Abstract

The invention discloses an internet-of-things system and method for optimizing production scheduling of a cutting bed and a cloth paving machine in a clothing factory, and belongs to the technical field of the internet-of-things system for the cutting bed and the cloth paving machine in the clothing factory. The technical problem of low productivity is solved. According to the technical scheme, the system is characterized in that an Internet of Things platform collects equipment data in real time and transmits the equipment data to a data analysis module through a network; the data analysis module is used for analyzing the collected data by utilizing a machine learning algorithm, predicting the production completion time and evaluating the equipment performance and the resource utilization rate; the intelligent production scheduling module is used for performing intelligent production scheduling by utilizing an AI technology based on a data analysis result, and automatically optimizing production task distribution of a cutting bed and a cloth paving machine; the real-time monitoring module is provided with a large-screen display system which is updated in real time and is used for displaying the production progress of the cutting bed and the cloth paving machine in real time; and the data report module is provided with a multifunctional report system, supports export in various formats and self-defined analysis, and has the effects of optimizing and improving productivity.

Description

Technical Field

[0001] The invention relates to the technical field of Internet of Things systems for cutting tables and cloth spreading machines, and in particular to an Internet of Things system and method for optimizing production scheduling of cutting tables and cloth spreading machines in a garment factory. Background Art

[0002] In the garment production process, cutting machines and cloth spreading machines are key equipment, and their working efficiency directly affects production capacity. Traditional production scheduling methods often rely on manual experience, and there are problems such as low scheduling efficiency, insufficient resource utilization, and difficulty in controlling production progress, which leads to extended production cycles and increased costs.

[0003] First of all, the manual production scheduling process is cumbersome and requires comprehensive consideration of multiple factors such as order information, equipment status, personnel arrangements, etc. The job learning cost is high, the learning cycle is long, and there is a high degree of dependence on on-the-job personnel. It is easy to make mistakes, resulting in low scheduling efficiency.

[0004] Secondly, traditional production scheduling methods make it difficult to effectively utilize equipment and personnel resources. For example, when the number of orders is large and the types are complex, it is difficult to reasonably allocate production tasks, resulting in some equipment being idle and uneven workload for personnel, causing waste of resources and increased production costs.

[0005] In addition, traditional production scheduling methods lack real-time monitoring, making it difficult to accurately grasp the production progress. For example, when equipment fails or personnel have problems, it is difficult to discover and adjust the production plan in time, resulting in delays in production progress and affecting production efficiency.

[0006] As competition in the clothing industry becomes increasingly fierce, the requirements for production efficiency and cost control are getting higher and higher. The traditional production scheduling method can no longer meet the needs of modern clothing production. Therefore, it is of great value to develop an IoT system and method that can optimize production scheduling, improve production efficiency, and reduce production costs. Summary of the invention

[0007] In order to solve the above-mentioned technical problems and shortcomings: low scheduling efficiency, insufficient resource utilization and difficult to control production progress of cutting beds and cloth spreading machines in garment factories, the present invention provides an Internet of Things system and method for optimizing the scheduling of cutting beds and cloth spreading machines in garment factories.

[0008] In order to achieve the above-mentioned purpose and other related purposes, the present invention adopts the following technical solutions:

[0009] An IoT system for optimizing production scheduling of cutting beds and cloth spreading machines in a clothing factory, comprising:

[0010] The IoT platform, including sensors, controllers, and communication modules, is used to connect the cutting bed and the cloth spreading machine, collect equipment status, production data, and order information data in real time, and transmit them to the data analysis module through the network;

[0011] Data acquisition module, used to obtain real-time data of cutting bed and cloth spreading machine from the IoT platform.

[0012] Data analysis module: Use machine learning algorithms to analyze the collected data, predict production completion time, evaluate equipment performance and resource utilization,

[0013] Intelligent production scheduling module: Based on data analysis results, AI technology is used for intelligent production scheduling, automatically optimizing the production task allocation of cutting beds and cloth spreading machines.

[0014] Real-time monitoring module: It has a large screen display system with real-time updates, which can display the production progress of the cutting bed and the spreading machine in real time.

[0015] Data reporting module: It has a multi-functional reporting system that supports export in multiple formats and customized analysis.

[0016] Preferably, an order middleware module is also included: after the order is imported, the order information transmitted from different systems of different customers is converted into a standard format that can be used in this system.

[0017] Preferably, the data acquisition module obtains the real-time data of the cutting bed and the cloth spreading machine from the Internet of Things platform, cleans and pre-processes the real-time data, and then provides it to the data analysis module.

[0018] The information output by the data analysis module is provided to the intelligent production scheduling module as decision-making data.

[0019] The intelligent production scheduling module receives the decision data from the data analysis module, automatically optimizes the production task allocation of the cutting bed and the cloth spreading machine, and gives priority to urgent orders and orders with good equipment performance.

[0020] The real-time monitoring module includes order completion status and equipment status information.

[0021] The multifunctional reporting system is used to generate reports including production progress reports and equipment utilization rate reports.

[0022] Preferably, the order middleware module includes:

[0023] Data receiving module: used to receive order data from different customers' MES systems, and perform preliminary analysis and format conversion.

[0024] Format conversion module: According to the preset mapping rules, it converts the data formats of different customer MES systems into a standard format compatible with this system.

[0025] Data verification module: Verify the converted data to ensure data accuracy and completeness.

[0026] Data storage module: stores the converted order data in the database of this system for use by other external order management modules;

[0027] The data receiving module, format conversion module, data verification module, and data storage module are connected via an API interface and a database interface, and an identity verification algorithm is used in the data transmission process.

[0028] Preferably, the order middleware module uses three steps of data analysis, format mapping and standard output to realize data transmission between different systems, including:

[0029] Through direct database access, first open the database permissions. The required connection information includes account name, password, port number, connection name and IP address, as well as the corresponding production record table. Direct database access can obtain order details including delivery time, creation time, order ID, order name, marker name, number of fabric layers, fabric length, number of pieces, size configuration, color and fabric type;

[0030] Through API docking, after the order is reported to the API, you can upload the order and files by yourself according to the API documentation.

[0031] Preferably, the intelligent production scheduling module comprises the following steps:

[0032] S1. Data collection operation: all production reports output by the cutting equipment are serialized and converted into JSON messages and sent to the server. The corresponding interface of the server receives the JSON message and stores it in the database persistence layer, waiting for retrieval;

[0033] S2. Data analysis operation,

[0034] S21. When the production scheduling end needs to schedule production, it will request the production data of the equipment from the server.

[0035] S22. After the request reaches the nearest week or month, a preliminary labor time forecast will be made based on the time and speed of completing the order;

[0036] S23, cutting bed prediction: by analyzing the path length and total completion time of the cutting bed cutting pattern, the cutting speed can be obtained. Based on the cutting speed and the daily number of completed orders, the average completion volume in the past week or month can be obtained. Combined with the redundancy value, the estimated speed of the cutting bed can be given.

[0037] S24, Marking machine prediction: Analyze the total time spent by the marking machine, the number of pieces in the layout, and get the average time it takes to mark a label. Combined with the redundancy value, the estimated working hours of the marking machine are given.

[0038] S25. Prediction of fabric spreading machine: Analyze the total time spent by the fabric spreading machine, the number of meters of fabric spread per unit time, and combine the redundancy value to give the time spent by the fabric spreading machine to complete the order.

[0039] S26. Send all predicted time data to the production scheduling end. The production scheduling end will predict the working hours of different equipment according to the length of the layout, the number of layers and the length of the cloth. The annealing algorithm will be used for scheduling and prediction, and the scheduling results will be output to the operator.

[0040] S27. After checking the forecast results, the operator confirms the production schedule and reports the order to the dispatch system. The production schedule is completed.

[0041] On the other hand, a method for optimizing production scheduling of cutting tables and cloth spreading machines in a garment factory is also provided, using the above-mentioned Internet of Things system.

[0042] In a third aspect, a method for optimizing production scheduling of a cutting bed and a cloth spreading machine in a garment factory is provided, comprising an intelligent production scheduling module and adopting the following steps:

[0043] S1. Data collection operation: all production reports output by the cutting equipment are serialized and converted into JSON messages and sent to the server. The corresponding interface of the server receives the JSON message and stores it in the database persistence layer, waiting for retrieval;

[0044] S2. Data analysis operation,

[0045] S21. When the production scheduling end needs to schedule production, it will request the production data of the equipment from the server.

[0046] S22. After the request reaches the nearest week or month, a preliminary labor time forecast will be made based on the time and speed of completing the order;

[0047] S23, cutting bed prediction: by analyzing the path length and total completion time of the cutting bed cutting pattern, the cutting speed can be obtained. Based on the cutting speed and the daily number of completed orders, the average completion volume in the past week or month can be obtained. Combined with the redundancy value, the estimated speed of the cutting bed can be given.

[0048] S24, Marking machine prediction: Analyze the total time spent by the marking machine, the number of pieces in the layout, and get the average time it takes to mark a label. Combined with the redundancy value, the estimated working hours of the marking machine are given.

[0049] S25. Prediction of fabric spreading machine: Analyze the total time spent by the fabric spreading machine, the number of meters of fabric spread per unit time, and combine the redundancy value to give the time spent by the fabric spreading machine to complete the order.

[0050] S26. Send all predicted time data to the production scheduling end. The production scheduling end will predict the working hours of different equipment according to the length of the layout, the number of layers and the length of the cloth. The annealing algorithm will be used for scheduling and prediction, and the scheduling results will be output to the operator.

[0051] S27. After checking the forecast results, the operator confirms the production schedule and reports the order to the dispatch system. The production schedule is completed.

[0052] In summary, the invention has at least one of the following beneficial technical effects:

[0053] 1. Open up the customer's production scheduling process: Order middleware serves as a bridge connecting different customers' MES systems with this system, realizing seamless connection of the customer's production scheduling process, ensuring that order information is delivered to the production link in a timely and accurate manner, and improving production efficiency.

[0054] 2. Electronic work order management: The order middleware converts the order information in the customer's MES system into an electronic work order, avoiding the problem of paper work orders being easily lost or damaged, realizing the electronic management of work order information, and improving information security.

[0055] 3. Reduce dependence on personnel: Through automated data conversion and intelligent scheduling functions, the dependence on the experience of scheduling personnel is reduced, the personnel training cost and learning curve are reduced, and work efficiency is improved.

[0056] 4. Strong compatibility: The order middleware adopts standardized data interfaces and mapping rules, and is compatible with a variety of different types of MES systems to meet the needs of different customers.

[0057] 5. Transparency of production progress: The order middleware links the order information in the customer's MES system with the production progress, and displays the production progress through the real-time monitoring module, making the production process more transparent and convenient for customers and enterprise managers to understand the production status in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a system module block diagram of an embodiment of the present invention;

[0059] Figure 2 It is a schematic diagram of data transmission in the order management process.

[0060] Description of the reference numerals of the main components:

[0061] 100. Internet of Things platform; 101. Sensor; 102. Controller; 103. Communication module; 200. Data acquisition module; 300. Data analysis module; 400. Intelligent production scheduling module; 500. Real-time monitoring module; 600. Data reporting module; 700. Order middleware module; 701. Data receiving module; 702. Format conversion module; 703. Data verification module; 704. Data storage module. DETAILED DESCRIPTION

[0062] The following is an explanation of the embodiments of the present invention by specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0063] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention. The illustrations only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0064] The specific implementation manner of the present invention will be further described below in conjunction with the accompanying drawings.

[0065] Embodiment 1:

[0066] The invention embodiment discloses an IoT system for optimizing production scheduling of cutting beds and cloth spreading machines in a clothing factory, referring to Figure 1 and Figure 2 As shown, including:

[0067] The Internet of Things platform 100 includes a sensor 101, a controller 102, and a communication module 103, which are used to connect the cutting table and the cloth spreading machine. The Internet of Things platform 100 is the overall management system of the Internet of Things. Through this system, various sensors 101 and devices can be easily connected and the data of these devices can be stored in the cloud, and then the data can be analyzed and processed, thereby providing users with an intelligent data platform. The equipment status, production data, and order information data are collected in real time and transmitted to the data analysis module 300 through the network.

[0068] The data acquisition module 200 is used to obtain real-time data of the cutting table and the cloth spreading machine from the Internet of Things platform 100. Real-time data refers to information that can be used for processing and analysis at the moment the data is generated or received. Compared with static or historical data, real-time data changes dynamically.

[0069] Data analysis module 300: Analyze the collected data using machine learning algorithms to predict production completion time and evaluate equipment performance and resource utilization. Machine learning algorithms are a type of algorithm that can automatically learn and improve from data and are widely used in fields such as data mining, pattern recognition, and predictive analysis. In this solution, an existing machine learning algorithm is used, so no in-depth explanation is given.

[0070] Intelligent production scheduling module 400: Based on the data analysis results, AI technology is used for intelligent production scheduling to automatically optimize the production task allocation of the cutting table and the cloth spreading machine. Artificial Intelligence (AI) refers to the technology and science of simulating human intelligence through computer systems. Artificial Intelligence is not just a single technology, but also includes deep learning, machine learning, computer vision, natural language processing and other technologies and algorithms. Specifically, those that are not related to this solution will not be explained in depth here.

[0071] Real-time monitoring module 500: A large-screen display system with real-time updates, which displays the production progress of the cutting table and the cloth spreading machine in real time.

[0072] Data Report Module 600: It has a multi-functional reporting system that supports multiple format exports and custom analysis.

[0073] The core of this solution is the order middleware module 700: after the order is imported, the order information transmitted from different systems of different customers is converted into a standard format that can be used in this system.

[0074] Specifically, after the data acquisition module 200 obtains the real-time data of the cutting bed and the cloth spreading machine from the Internet of Things platform 100, it cleans and preprocesses the real-time data and then provides it to the data analysis module 300. Cleaning and preprocessing of real-time data are key steps to ensure data quality and analysis accuracy. Through cleaning and preprocessing, noise can be removed, errors can be corrected, missing values ​​can be processed, data formats can be converted, etc., thereby providing a high-quality data foundation for subsequent data analysis and machine learning model training.

[0075] Now let's briefly explain this step. The main steps of real-time data cleaning and preprocessing are data cleaning:

[0076] De-duplicate data: Identify and remove duplicate records in a data set to ensure data uniqueness.

[0077] Handling missing values: Depending on the data characteristics and analysis requirements, you can choose to delete, fill, or impute missing values.

[0078] Dealing with outliers: Identify and deal with outliers in the data, possibly by removing, correcting, or transforming them to reduce their impact on the analysis results.

[0079] Data conversion:

[0080] Format and type conversion: Convert data into a format suitable for analysis, such as converting date and time data into a unified date and time format, converting text data into numeric codes, etc.

[0081] Data standardization: Adjust the scale of numerical data so that they are at the same level. Commonly used methods include minimum-maximum standardization and Z-score standardization.

[0082] Data reduction: Reducing the size and complexity of a dataset by selecting or extracting the most important features of the data while trying to preserve the original information of the data.

[0083] Data storage: Store the preprocessed data in a real-time database for subsequent analysis and query.

[0084] Data quality verification: After each processing step, data quality checks are performed to ensure that the cleaning operation has not introduced new problems and has improved the overall quality of the data.

[0085] The information output by the data analysis module 300 is provided to the intelligent production scheduling module 400 as decision-making data.

[0086] The intelligent production scheduling module 400 receives the decision data from the data analysis module 300, automatically optimizes the production task allocation of the cutting table and the cloth spreading machine, and gives priority to urgent orders and orders with good equipment performance.

[0087] The real-time monitoring module 500 includes order completion status and equipment status information.

[0088] Multifunctional reporting system, used to generate reports including production progress report and equipment utilization report.

[0089] More specifically, the order middleware module 700 includes:

[0090] Data receiving module 701: used to receive order data from different customer MES systems, and perform preliminary analysis and format conversion.

[0091] Format conversion module 702: According to the preset mapping rules, the data formats of different customer MES systems are converted into a standard format compatible with this system. The MES system, namely the Manufacturing Execution System, is a production information management system for the workshop execution layer of manufacturing enterprises. The application of this system in the industry is public content, so no further explanation is given.

[0092] Data verification module 703: Verify the converted data to ensure data accuracy and completeness.

[0093] Data storage module 704: stores the converted order data in the database of this system for use by other external order management modules.

[0094] The data receiving module 701, the format conversion module 702, the data verification module 703, and the data storage module 704 are connected through the API interface and the database interface, and the data transmission process adopts the identity verification algorithm. The API interface, namely the application programming interface (Application Programming Interface), is a set of predefined functions, protocols and tools, which is designed to provide application programs and developers with the ability to access a set of routines based on certain software or hardware without accessing the source code.

[0095] The functions of the API interface are:

[0096] Connecting the front-end and back-end: The API interface is a bridge between the front-end application and the back-end server, allowing the front-end to implement data interaction and function implementation by calling the API provided by the back-end.

[0097] Data exchange: The API interface enables data exchange between different software systems, realizing information sharing and functional integration.

[0098] Simplify development: By using APIs, developers can quickly integrate third-party services, reduce the workload of repetitive development, and improve development efficiency.

[0099] In the order middleware module 700, three steps of data parsing, format mapping and standard output are adopted to realize data transmission between different systems, including:

[0100] Through direct database access, first open the database permissions. The required connection information includes account name, password, port number, connection name and IP address, as well as the corresponding production record table. Direct database access can obtain order details including delivery time, creation time, order ID, order name, marker name, number of fabric layers, fabric length, number of pieces, size configuration, color and fabric type;

[0101] Through API docking, after the order is reported to the API, you can upload the order and files by yourself according to the API documentation.

[0102] In this solution, the intelligent production scheduling module 400 includes the following steps:

[0103] S1. Data collection operation: All production reports output by the cutting equipment are serialized and converted into JSON messages and sent to the server. The corresponding interface of the server receives the JSON message and stores it in the database persistence layer, waiting for retrieval. JSON (JavaScript Object Notation) is a lightweight data exchange format that is easy for people to read and write, and easy for machines to parse and generate. It is based on a subset of JavaScript, but is independent of any programming language, which makes JSON an ideal choice for data exchange between different platforms and systems.

[0104] S2. Data analysis operations are as follows:

[0105] S21. When the production scheduling end needs to schedule production, it will request the production data of the equipment from the server.

[0106] S22. After the request reaches the nearest week or month, a preliminary labor time forecast will be made based on the time and speed of completing the order;

[0107] S23. Cutting bed prediction: By analyzing the path length and total completion time of the cutting bed cutting pattern, the cutting speed can be obtained. According to the cutting speed and the daily completion volume, the average completion volume in the past week or month can be obtained. Combined with the redundancy value, the estimated speed of the cutting bed is given; the redundancy value refers to unnecessary duplicate data or information during data storage or transmission. Redundancy may be caused by a variety of reasons, including unreasonable design, improper data duplication or update, etc. Data normalization: Reduce data redundancy by decomposing data into multiple tables and associating them through foreign keys. Data cleaning: Delete duplicate records and correct erroneous data to improve data quality.

[0108] S24, Marking machine prediction: Analyze the total time spent by the marking machine, the number of pieces in the layout, and get the average time it takes to mark a label. Combined with the redundancy value, the estimated working hours of the marking machine are given.

[0109] S25. Prediction of fabric spreading machine: Analyze the total time spent by the fabric spreading machine, the number of meters of fabric spread per unit time, and combine the redundancy value to give the time spent by the fabric spreading machine to complete the order.

[0110] S26. Send all predicted time data to the production scheduling end, which will predict the working hours of different equipment according to the length of the layout, the number of layers and the length, use the annealing algorithm for scheduling and prediction, and output the scheduling results to the operator. The annealing algorithm is an existing algorithm. As a powerful global optimization tool, the annealing algorithm shows unique advantages in solving complex optimization problems. By applying the annealing algorithm, the global optimal solution of the problem can be effectively found, and the optimization efficiency and performance can be improved.

[0111] S27. After checking the forecast results, the operator confirms the production schedule and reports the order to the dispatch system. The production schedule is completed.

[0112] refer to Figure 2 Understand that the advantages of this solution are reflected in the following aspects:

[0113] 1. Open up the customer's production scheduling process: Order middleware serves as a bridge connecting different customers' MES systems with this system, realizing seamless connection of the customer's production scheduling process, ensuring that order information is delivered to the production link in a timely and accurate manner, and improving production efficiency.

[0114] 2. Electronic work order management: The order middleware converts the order information in the customer's MES system into an electronic work order, avoiding the problem of paper work orders being easily lost or damaged, realizing the electronic management of work order information, and improving information security.

[0115] 3. Reduce dependence on personnel: Through automated data conversion and intelligent scheduling functions, the dependence on the experience of scheduling personnel is reduced, the personnel training cost and learning curve are reduced, and work efficiency is improved.

[0116] 4. Strong compatibility: The order middleware adopts standardized data interfaces and mapping rules, and is compatible with a variety of different types of MES systems to meet the needs of different customers.

[0117] 5. Transparency of production progress: The order middleware associates the order information in the customer's MES system with the production progress, and displays the production progress through the real-time monitoring module 500, making the production process more transparent and convenient for customers and enterprise managers to understand the production status in a timely manner.

[0118] Embodiment 2:

[0119] Based on the above-mentioned embodiment 1, a method for optimizing production scheduling of cutting tables and cloth spreading machines in a garment factory is also provided, which adopts the above-mentioned Internet of Things system.

[0120] Embodiment three:

[0121] Based on the above embodiment, a method for optimizing production scheduling of cutting beds and cloth spreading machines in a garment factory can also be provided separately, including an intelligent production scheduling module 400, and using the following steps:

[0122] S1. Data collection operation: all production reports output by the cutting equipment are serialized and converted into JSON messages and sent to the server. The corresponding interface of the server receives the JSON message and stores it in the database persistence layer, waiting for retrieval;

[0123] S2. Data analysis operation,

[0124] S21. When the production scheduling end needs to schedule production, it will request the production data of the equipment from the server.

[0125] S22. After the request reaches the nearest week or month, a preliminary labor time forecast will be made based on the time and speed of completing the order;

[0126] S23, cutting bed prediction: by analyzing the path length and total completion time of the cutting bed cutting pattern, the cutting speed can be obtained. Based on the cutting speed and the daily number of completed orders, the average completion volume in the past week or month can be obtained. Combined with the redundancy value, the estimated speed of the cutting bed can be given.

[0127] S24, Marking machine prediction: Analyze the total time spent by the marking machine, the number of pieces in the layout, and get the average time it takes to mark a label. Combined with the redundancy value, the estimated working hours of the marking machine are given.

[0128] S25. Prediction of fabric spreading machine: Analyze the total time spent by the fabric spreading machine, the number of meters of fabric spread per unit time, and combine the redundancy value to give the time spent by the fabric spreading machine to complete the order.

[0129] S26. Send all predicted time data to the production scheduling end. The production scheduling end will predict the working hours of different equipment according to the length of the layout, the number of layers and the length of the cloth. The annealing algorithm will be used for scheduling and prediction, and the scheduling results will be output to the operator.

[0130] S27. After checking the forecast results, the operator confirms the production schedule and reports the order to the dispatch system. The production schedule is completed.

[0131] Since the above process has been explained and illustrated, it will not be repeated in this embodiment.

[0132] The above embodiments are only illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present invention. Therefore, any equivalent changes made to the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An IoT system for optimizing production scheduling of cutting machines and cloth spreading machines in a garment factory, characterized in that: include: The IoT platform, including sensors, controllers, and communication modules, is used to connect the cutting bed and the cloth spreading machine, collect equipment status, production data, and order information data in real time, and transmit them to the data analysis module through the network; Data acquisition module, used to obtain real-time data of cutting bed and cloth spreading machine from the IoT platform. Data analysis module: Use machine learning algorithms to analyze the collected data, predict production completion time, evaluate equipment performance and resource utilization, Intelligent production scheduling module: Based on data analysis results, AI technology is used for intelligent production scheduling, automatically optimizing the production task allocation of cutting beds and cloth spreading machines. Real-time monitoring module: It has a large screen display system with real-time updates, which can display the production progress of the cutting bed and the spreading machine in real time. Data reporting module: It has a multi-functional reporting system that supports export in multiple formats and customized analysis.

2. The IoT system for optimizing production scheduling of cutting machines and cloth spreading machines in a garment factory according to claim 1 is characterized in that: It also includes an order middleware module: after the order is imported, the order information transmitted from different systems of different customers is converted into a standard format that can be used in this system.

3. The IoT system for optimizing production scheduling of cutting machines and cloth spreading machines in a garment factory according to claim 1 is characterized in that: The data acquisition module obtains the real-time data of the cutting bed and the cloth spreading machine from the Internet of Things platform, cleans and pre-processes the real-time data, and then provides it to the data analysis module. The information output by the data analysis module is provided to the intelligent production scheduling module as decision-making data. The intelligent production scheduling module receives the decision data from the data analysis module, automatically optimizes the production task allocation of the cutting bed and the cloth spreading machine, and gives priority to urgent orders and orders with good equipment performance. The real-time monitoring module includes order completion status and equipment status information. The multifunctional reporting system is used to generate reports including production progress reports and equipment utilization rate reports.

4. The IoT system for optimizing production scheduling of cutting machines and cloth spreading machines in a garment factory according to claim 2 is characterized in that: The order middleware module includes: Data receiving module: used to receive order data from different customers' MES systems, and perform preliminary analysis and format conversion. Format conversion module: According to the preset mapping rules, it converts the data formats of different customer MES systems into a standard format compatible with this system. Data verification module: Verify the converted data to ensure data accuracy and completeness. Data storage module: stores the converted order data in the database of this system for use by other external order management modules; The data receiving module, format conversion module, data verification module, and data storage module are connected via an API interface and a database interface, and an identity verification algorithm is used in the data transmission process.

5. The IoT system for optimizing production scheduling of cutting machines and cloth spreading machines in a garment factory according to claim 4 is characterized in that: The order middleware module uses three steps of data analysis, format mapping and standard output to achieve data transmission between different systems, including: Through direct database access, first open the database permissions. The required connection information includes account name, password, port number, connection name and IP address, as well as the corresponding production record table. Direct database access can obtain order details including delivery time, creation time, order ID, order name, marker name, number of fabric layers, fabric length, number of pieces, size configuration, color and fabric type; Through API docking, after the order is reported to the API, you can upload the order and files by yourself according to the API documentation.

6. The IoT system for optimizing production scheduling of cutting machines and cloth spreading machines in a garment factory according to claim 1 is characterized in that: The intelligent production scheduling module includes the following steps: S1. Data collection operation: all production reports output by the cutting equipment are serialized and converted into JSON messages and sent to the server. The corresponding interface of the server receives the JSON message and stores it in the database persistence layer, waiting for retrieval; S2. Data analysis operation, S21. When the production scheduling end needs to schedule production, it will request the production data of the equipment from the server. S22. After the request reaches the nearest week or month, a preliminary labor time forecast will be made based on the time and speed of completing the order; S23, cutting bed prediction: by analyzing the path length and total completion time of the cutting bed cutting pattern, the cutting speed can be obtained. Based on the cutting speed and the daily number of completed orders, the average completion volume in the past week or month can be obtained. Combined with the redundancy value, the estimated speed of the cutting bed can be given. S24, Marking machine prediction: Analyze the total time spent by the marking machine, the number of pieces in the layout, and get the average time it takes to mark a label. Combined with the redundancy value, the estimated working hours of the marking machine are given. S25. Prediction of fabric spreading machine: Analyze the total time spent by the fabric spreading machine, the number of meters of fabric spread per unit time, and combine the redundancy value to give the time spent by the fabric spreading machine to complete the order. S26. Send all predicted time data to the production scheduling end. The production scheduling end will predict the working hours of different equipment according to the length of the layout, the number of layers and the length of the cloth. The annealing algorithm will be used for scheduling and prediction, and the scheduling results will be output to the operator. S27. After checking the forecast results, the operator confirms the production schedule and reports the order to the dispatch system. The production schedule is completed.

7. A method for optimizing production scheduling of cutting machines and cloth spreading machines in a garment factory, characterized in that: Adopt the Internet of Things system as claimed in any one of claims 1 to 6.

8. A method for optimizing production scheduling of cutting machines and cloth spreading machines in a garment factory, characterized in that: It includes the intelligent production scheduling module and adopts the following steps: S1. Data collection operation: all production reports output by the cutting equipment are serialized and converted into JSON messages and sent to the server. The corresponding interface of the server receives the JSON message and stores it in the database persistence layer, waiting for retrieval; S2. Data analysis operation, S21. When the production scheduling end needs to schedule production, it will request the production data of the equipment from the server. S22. After the request reaches the nearest week or month, a preliminary labor time forecast will be made based on the time and speed of completing the order; S23, cutting bed prediction: by analyzing the path length and total completion time of the cutting bed cutting pattern, the cutting speed can be obtained. Based on the cutting speed and the daily number of completed orders, the average completion volume in the past week or month can be obtained. Combined with the redundancy value, the estimated speed of the cutting bed can be given. S24, Marking machine prediction: Analyze the total time spent by the marking machine, the number of pieces in the layout, and get the average time it takes to mark a label. Combined with the redundancy value, the estimated working hours of the marking machine are given. S25. Prediction of fabric spreading machine: Analyze the total time spent by the fabric spreading machine, the number of meters of fabric spread per unit time, and combine the redundancy value to give the time spent by the fabric spreading machine to complete the order. S26. Send all predicted time data to the production scheduling end. The production scheduling end will predict the working hours of different equipment according to the length of the layout, the number of layers and the length of the cloth. The annealing algorithm will be used for scheduling and prediction, and the scheduling results will be output to the operator. S27. After checking the forecast results, the operator confirms the production schedule and reports the order to the dispatch system. The production schedule is completed.

Images